← Anthropic

Agent report card

Can an agent use Anthropic API through API service lifecycle?

Grade B: Machine credentials exist but require manual copying, broad authority, or weak lifecycle support.

Observedrev sha256:ce068885cdcb…barrier checks 0/5 verified

Agent ReadinessBLimited

Five-stage assessment

Where agent autonomy holds and where it breaks

Five states · each from its own evidence · lifecycle order, not a journey
  1. EvaluateReady
  2. Sign upLimited
  3. PayReady
  4. ProvisionLimited
  5. OperateLimited
  1. 01

    Evaluate

    Ready

    The exact service and stable evaluation or access entrypoints are publicly discoverable.

    The exact Claude API service and stable entrypoints (including official ant CLI, client SDKs in 7 languages, and Messages API documentation) are publicly discoverable on the Claude Platform Docs.

    Applicable terms are stable, readable, retrievable, and materially complete.

    Eligibility conditions and required inputs are explicit and decidable.

    Price or no-charge status, variables, currency, and material conditions are explicit.

    Evidence and actions6 signals

    Can an agent decide every material eligibility condition before commitment?

    supported: fresh

    Eligibility conditions and required inputs are explicit and decidable.

    Anthropic defines Commercial Terms of Service governing access to Anthropic API keys and related tools for Customer (or the entity represented by an authorized person). The terms explicitly state they are not for consumer use and specify entity representation authority requirements.

    eligibility_decidability: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent estimate cost or confirm no-charge status before commitment?

    supported: fresh

    Price or no-charge status, variables, currency, and material conditions are explicit.

    Pricing for the Claude API is explicitly provided in USD, detailing standard per-model/per-feature token usage rates, additional code execution container time ($0.05 USD per hour after 1,550 free hours/month), and monthly usage billing.

    pricing_decidability: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent find the exact service and its stable entrypoints?

    supported: fresh

    The exact service and stable evaluation or access entrypoints are publicly discoverable.

    The exact Claude API service and stable entrypoints (including official ant CLI, client SDKs in 7 languages, and Messages API documentation) are publicly discoverable on the Claude Platform Docs.

    service_discovery: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Are verified structured discovery artifacts available?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The retained excerpts for Anthropic API are human documentation pages; they contain no first-party statement that structured discovery artifacts are absent, and no artifact was captured or verified either way.

    structured_evaluation_discovery: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent retrieve and understand the applicable commitment terms?

    supported: fresh

    Applicable terms are stable, readable, retrievable, and materially complete.

    Applicable Commercial Terms of Service are stable, readable, retrievable, and complete, incorporating referenced policies such as the Usage Policy, Supported Regions Policy, and Model Pricing Page.

    terms_access: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Does the vendor deliberately describe access for web agents?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The retained excerpts for Anthropic API do not state a web-agent or crawler access policy for the assessed resources in either direction.

    verified_web_agent_access: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

  2. 02

    Sign up

    Limited

    Machine credentials exist but require manual copying, broad authority, or weak lifecycle support.

    First-party documentation explicitly details machine credentials including Console API keys and short-lived Workload Identity Federation tokens, but API key generation requires manual creation in Console Account Settings.

    A stable canonical route begins the required access bootstrap.

    Evidence and actions5 signals

    Can an agent operate the access controls and safe handoffs deterministically?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The sign-in page displays buttons to continue with Google, email, or SSO, but current admissible evidence does not establish whether required validation and handoffs are fully machine-operable.

    access_control_operability: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Is there a stable route to begin obtaining service access?

    supported: fresh

    A stable canonical route begins the required access bootstrap.

    A stable access entrypoint to the platform is directly observed via the sign-in page at platform.claude.com/login.

    access_entrypoint_stability: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent obtain access without an unsupported CAPTCHA boundary?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    No CAPTCHA challenge is directly observed on the captured sign-in page, but current admissible evidence does not resolve whether a CAPTCHA boundary exists across the flow.

    captcha_compatible_access: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent obtain scoped, revocable authority for this service?

    supported: fresh

    Machine credentials exist but require manual copying, broad authority, or weak lifecycle support.

    First-party documentation explicitly details machine credentials including Console API keys and short-lived Workload Identity Federation tokens, but API key generation requires manual creation in Console Account Settings.

    delegated_identity_access: Limited: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can required phone verification be completed through a supported boundary?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    Current admissible evidence from the sign-in page does not mention phone verification or resolve whether phone verification is required.

    phone_verification_compatible: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    What would improve this stage

    • Provide scoped delegated authorization with consent, revocation, and deterministic resumption.
  3. 03

    Pay

    Ready

    Charge or no-charge status, currency, recurrence, and material conditions are disclosed.

    The platform pricing documentation and API billing guide disclose the commercial commitment terms, stating that API usage is billed in USD based on actual monthly usage or CCU rate conversions ($0.01 per CCU), with arrears or prepaid options explained prior to charge.

    A documented direct purchase path reaches paid access without a vendor decision point.

    Evidence and actions4 signals

    Can an agent construct checkout, hand off approval safely, and resume?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The retained evidence describes monthly invoicing and credit auto-reload options for Claude API usage, but it does not establish a deterministic flow for an agent to construct checkout, hand off approval safely, and resume.

    checkout_operability: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Is the exact commercial commitment disclosed before authorization?

    supported: fresh

    Charge or no-charge status, currency, recurrence, and material conditions are disclosed.

    The platform pricing documentation and API billing guide disclose the commercial commitment terms, stating that API usage is billed in USD based on actual monthly usage or CCU rate conversions ($0.01 per CCU), with arrears or prepaid options explained prior to charge.

    commitment_disclosure: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can payment be authorized within scoped agent or explicit human authority?

    supported: fresh

    Current admissible evidence does not resolve this finding.

    The retained evidence explains how an Admin or Billing role can update card details in the Claude Console settings, but it does not document a programmatic rail for scoped agent delegation or explicit human-confirmed authorization with receipts.

    payment_authorization: Unknown: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Is a direct self-service path to paid access documented?

    supported: fresh

    A documented direct purchase path reaches paid access without a vendor decision point.

    A direct self-service path to paid API access is documented via the Claude Console, where users can buy prepaid usage credits or set up payment methods under Settings > Billing without requiring a sales intervention.

    self_service_purchase: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

  4. 04

    Provision

    Limited

    Delivery needs additional human transfer or has weak scope or lifecycle semantics.

    The API overview states that API keys are generated in Account Settings within the web Console, where key type and expiration are chosen upon creation. Because key generation is handled manually through a web dashboard, delivery requires human transfer.

    Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

    A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.

    Evidence and actions3 signals

    Can usable access material be delivered securely to an authorized agent?

    supported: fresh

    Delivery needs additional human transfer or has weak scope or lifecycle semantics.

    The API overview states that API keys are generated in Account Settings within the web Console, where key type and expiration are chosen upon creation. Because key generation is handled manually through a web dashboard, delivery requires human transfer.

    access_material_delivery: Limited: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent determine successful provisioning completion and reconcile asynchronous failure?

    supported: fresh

    A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.

    The Messages API creates messages synchronously, returning a usable message object with an id, generated content blocks, model ID, and a stop_reason (such as end_turn), providing immediate synchronous provisioning completion and usable resource output.

    provisioning_completion: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can provisioning be initiated within supported agent authority?

    supported: fresh

    Provisioning is machine-triggerable or follows deterministically from an allowed handoff.

    Messages creation is initiated within supported agent authority via a direct programmatic POST request to /v1/messages.

    provisioning_operability: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    What would improve this stage

    • Deliver scoped access material through a secure documented machine-usable flow.
  5. 05

    Operate

    Limited

    Safe failure handling is documented only partially.

    Anthropic documents HTTP error codes, error shapes and SDK retries with exponential backoff honoring retry-after; the selected quotes do not establish idempotency or reconciliation semantics for the Messages operation.

    Only part of the credential lifecycle is agent-operable.

    Every essential target has a stable documented agent-usable interface alternative.

    Request-time authentication is documented and usable under scoped agent authority.

    Essential operations have stable readable request, response, and effect semantics.

    A verified agent-native interface covers the declared assessment targets.

    Evidence and actions6 signals

    Is an agent-native protocol interface verified against the essential targets?

    supported: fresh

    A verified agent-native interface covers the declared assessment targets.

    The Claude API provides explicit agent-native protocol interfaces and agent lifecycle tooling across Messages, Managed Agents (agents, sessions, environments), and Claude Agent SDK.

    agent_protocol_interface: Ready: tested 6 Sept

    • api-service

    Method public-semantic-assessment 2026-09-06

    Can an agent manage credential expiry, rotation, revocation, compromise, and recovery?

    supported: fresh

    Only part of the credential lifecycle is agent-operable.

    API keys are created in the Console with selectable key types and expiration times. API keys or tunnel tokens can be rotated or deleted/archived, but complete programmatic agent-driven credential lifecycle and compromise recovery are not established.

    credential_lifecycle: Limited: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent handle applicable failure modes safely?

    supported: fresh

    Safe failure handling is documented only partially.

    Anthropic documents HTTP error codes, error shapes and SDK retries with exponential backoff honoring retry-after; the selected quotes do not establish idempotency or reconciliation semantics for the Messages operation.

    failure_contract: Limited: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Can an agent authenticate service operations with scoped authority?

    supported: fresh

    Request-time authentication is documented and usable under scoped agent authority.

    Requests to the Claude API authenticate via Bearer token in the Authorization header or via the x-api-key header, with optional anthropic-workspace-id header to scope operations to a workspace.

    operation_authentication: Ready: tested 6 Sept

    Method public-semantic-assessment 2026-09-06

    Are essential operation inputs, outputs, and effects stable and decidable?

    supported: fresh

    Essential operations have stable readable request, response, and effect semantics.

    Essential API endpoints, parameters, request size limits, error shapes, SDK interfaces, and rate/spend limit response payloads are documented with stable semantics.

    operation_contract: Ready: tested 6 Sept

    • api-service

    Method public-semantic-assessment 2026-09-06

    Can an agent perform every essential assessment target through a usable interface?

    supported: fresh

    Every essential target has a stable documented agent-usable interface alternative.

    Every target feature and endpoint can be invoked using standard HTTP API requests, ant CLI, or official client SDKs.

    target_interface_access: Ready: tested 6 Sept

    • api-service

    Method public-semantic-assessment 2026-09-06

    What would improve this stage

    • Document applicable structured errors, retry, cancellation, and reconciliation semantics.
    • Provide scoped expiry, rotation, revocation, compromise, and recovery operations.

What works

  • Evaluate: The exact service and stable evaluation or access entrypoints are publicly discoverable.
  • Pay: Charge or no-charge status, currency, recurrence, and material conditions are disclosed.

What blocks agents

No stage is established as blocked.

Where autonomy is limited

  • Sign up: Machine credentials exist but require manual copying, broad authority, or weak lifecycle support.
  • Provision: Delivery needs additional human transfer or has weak scope or lifecycle semantics.
  • Operate: Safe failure handling is documented only partially.

What this grade establishes

14 of 14 graded signals have current supporting evidence. 0 of 5 additional barrier checks are verified.Unknown checks are not a pass or a confirmed blocker. This report is not proof of an end-to-end purchase or service session.

How the grade is derived

A through C grades count Limited stages; D and F reflect Blocked stages by lifecycle severity.

Coverage is complete only when every graded signal has supported, fresh, non-conflicting evidence. Barrier and informational signals do not change coverage; only fresh, supported barrier values that passed their admission evidence rule participate in stage outcomes.

Each stage takes its worst graded signal or verified barrier. A fresh, supported mandatory barrier that passed its admission evidence rule can block that stage; incomplete or stale barrier evidence remains context only. The overall grade is derived from the five stage states.

Startup offers

Anthropic on the startup-offers board

Distribution

The grade’s badge

One stable image resolving the record’s current live facts, linking to the canonical page. Embed it once; it keeps itself current. Placement is never evidence and never affects rank.

Live sourcey badge for Anthropic Agent Readiness grade B
[![sourcey record](https://sourcey.com/badges/agent-readiness/arp_01kzf0m4x54qzpnr923g24x6x8.svg)](https://sourcey.com/log/anthropic/agent-readiness/anthropic-api/api-service-lifecycle)

Improve the report

Correct it, rerun it, or improve the funnel.

Profile
arp_01kzf0m4x54qzpnr923g24x6x8
Projection
sha256:fce93178bab30388492a7ffeaccca7c9366ce12e33334c2e34ebfc35a3a8a577
Policy
service-use-2026-09-07-blocking-barriers-r12 · sha256:fc9e8f046d86fcf19ab2f1bc547219e503cdc11ffa135d020db7285965cd7d1d